SAINT-ACC:Safety-AwareIntelligentAdaptiveCruiseControlforAutonomousVehiclesUsingDeepReinforcementLearningLokeshDas1MyounggyuWon1Abstractenhancingtrafficflow,overlookingtheimpactofadaptiveadjustment...
ReinforcementLearningofImplicitandExplicitControlFlowinInstructionsEthanA.Brooks1JanarthananRajendran1RichardL.Lewis2SatinderSingh1AbstracttaskinstructionsthatrequiretheagenttolearnControlfloweithe...
ParallelDropletControlinMEDABiochipsUsingMulti-AgentReinforcementLearningTung-CheLiang1JinZhou1Yun-ShengChan2Tsung-YiHo3KrishnenduChakrabarty1Chen-YiLee2Abstract1.IntroductionMicrofluidicbiochipsar...
PAPRIKA:PrivateOnlineFalseDiscoveryRateControlWanrongZhang1GautamKamath2RachelCummings3Abstractoflarge-scaledatasetsandeaseofdataanalysis,whilebene-ficialtosociety,hascreatedaseverecrisisofreproduc...
OnlineOptimizationinGamesviaControlTheory:ConnectingRegret,PassivityandPoincare´RecurrenceYunKuenCheung1GeorgiosPiliouras2Abstracttheoryandonlineoptimization.WepresentanovelControl-theoreticunders...
Model-basedReinforcementLearningforContinuousControlwithPosteriorSamplingYingFan1YifeiMing1AbstractinRLhasbeenoneofthemainchallenges:theagentisexpectedtobalancebetweenexploringunseenstate-actionBal...
LocallyPersistentExplorationinContinuousControlTaskswithSparseRewardsSusanAmin12MaziarGomrokchi12HosseinAboutalebi34HarshSajita12DoinaPrecup12Abstractcallforacleverexplorationstrategythatexposesthe...
DeepCoherentExplorationforContinuousControlYijieZhang1HerkevanHoof2Abstractstrategiesandundirectedstrategies(Thrun,1992;Plappertetal.,2018).Whiledirectedstrategiesaimtoextractuse-Inpolicysearchmeth...
Dropout:ExplicitFormsandCapacityControlRamanArora1PeterBartlett2PooryaMianjy1NathanSrebro3Abstracttion(Cavazzaetal.,2018;Mianjyetal.,2018),intwolayerlinearnetworks(Mianjyetal.,2018),andindeeplinear...
ConsensusControlforDecentralizedDeepLearningLingjingKong1TaoLin1AnastasiaKoloskova1MartinJaggi1SebastianU.Stich1Abstractlocalmini-batchgradientscomputedondifferentsubsetsofthedata,forthelatersynchr...
ARegretMinimizationApproachtoIterativeLearningControlNamanAgarwal1EladHazan12AnirudhaMajumdar12KaranSingh3Abstractoffactors.Theprimarychallengewefocusoninthispa-peristheexistenceofunmodeleddeviatio...
ScalableDifferentiablePhysicsforLearningandControlYi-LingQiao1JunbangLiang1VladlenKoltun2MingC.Lin1AbstractRecenteffortshavesignificantlyadvancedtheunderstandingofdifferentiablephysicsinmachinelear...
SampleFactory:Egocentric3DControlfromPixelsat100000FPSwithAsynchronousReinforcementLearningAlekseiPetrenko12ZhehuiHuang2TusharKumar2GauravSukhatme2VladlenKoltun1AbstractHwangboetal.,2019;Molchanove...
PredictiveCodingforLocally-LinearControlRuiShu1TungNguyen2YinlamChow3TuanPham2KhoatThan2MohammadGhavamzadeh4StefanoErmon1HungBui2Abstractmonapproachistoemployvariousheuristicstoembedthehigh-dimensi...
OnlineControloftheFalseCoverageRateandFalseSignRateAsafWeinstein1AadityaRamdas2AbstractcanbesummarizedbytheobservationXt∼N(θt,1),in-dependentofallthepreviousobservations{Xi}i<t.Thereproducibility...
NeuralNetworkControlPolicyVerificationwithPersistentAdversarialPerturbationsYuh-ShyangWang1Tsui-WeiWeng2LucaDaniel2Abstractneuralnetworksaresurprisinglyvulnerabletoadversarialexamplesandattacks(Hua...
LogarithmicRegretforAdversarialOnlineControlDylanJ.Foster1MaxSimchowitz2Abstractbyawell-behavedstochasticprocessordrivenbyaworst-caseprocesstowhichthelearnermustremainrobustinWeintroduceanewalgorit...
InferringDQNstructureforhigh-dimensionalcontinuousControlAndreySakryukin1ChedyRa¨ıssi23MohanS.Kankanhalli1Abstract(Yunetal.,2017),NLP(Lietal.,2016)andothers,werepublished.Oneofthemainfocusesofrec...
FamilywiseErrorRateControlbyInteractiveUnmaskingBoyanDuan1AadityaRamdas12LarryWasserman12Abstractwhenµ<0,ithasnondecreasingdensity.Alowp-valuesuggestsevidencetorejectthenullhypothesis.Weproposeame...
ControlFrequencyAdaptationviaActionPersistenceinBatchReinforcementLearningAlbertoMariaMetelli1FlavioMazzolini1LorenzoBisi12LucaSabbioni12MarcelloRestelli12Abstractcontinuous–timeMDPs(Bradtke&Duff,...